WO2020181413A1

WO2020181413A1 - Endoscopic fluorescence system image processing method and apparatus, and storage medium

Info

Publication number: WO2020181413A1
Application number: PCT/CN2019/077482
Authority: WO
Inventors: 迟崇巍; 田捷
Original assignee: 北京数字精准医疗科技有限公司
Priority date: 2019-03-08
Filing date: 2019-03-08
Publication date: 2020-09-17

Abstract

Provided in the embodiments of the present application are an endoscopic fluorescence system image processing method and apparatus, and a storage medium. The method comprises: acquiring an image to be processed; performing image enhancement on the image to be processed; performing colour correction on the image after image enhancement; and performing fluorescence marking on the colour corrected image to acquire a colour image having a fluorescent display. The embodiments of the present invention can make the image displayed by an endoscopic fluorescence system more accurately reflect the real conditions of the probed area.

Description

Image processing method, device and storage medium of endoscopic fluorescence system

Technical field

This application relates to the field of image processing technology, and in particular to an image processing method, device and storage medium of an endoscopic fluorescent system.

Background technique

In recent years, due to the continuous development of molecular imaging technology, following radionuclide imaging, positron emission tomography, single photon emission computed tomography and magnetic resonance imaging, high-resolution optical imaging has emerged, among which near-infrared fluorescence imaging Be concerned. Because the ability of light to penetrate tissues is related to the strength of the tissues to absorb light, the characteristics of light waves, the structure of biological tissues and their physical and chemical properties. 650～900nm Near-Infrared (Near-Infrared, referred to as NIR) is called "Tissue Optical Window". Compared with visible light, it has: (1) The absorption and scattering effects of biological tissues in this band of near-infrared light The smallest, compared with visible light, near-infrared light can penetrate deeper tissues; ⑵Because the autofluorescence of biological tissues in this band of near-infrared light is small, the signal-to-background ratio (SBR) is relatively high and other advantages .

The single-camera endoscopic fluorescence system currently on the market can only display black-and-white images or pseudo-color images. Such black-and-white images or pseudo-color images cannot accurately reflect the real situation of the detected area, which may easily lead to Unable to accurately judge the tissue structure and blood flow.

Summary of the invention

The purpose of the embodiments of the present application is to provide an image processing method, device, and storage medium of an endoscopic fluorescence system, so that the image displayed by the endoscopic fluorescence system can more accurately reflect the real situation of the detected area.

To achieve the foregoing objective, on the one hand, an embodiment of the present application provides an image processing method of an endoscopic fluorescence system, including:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

Perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.

In an embodiment, the performing image enhancement on the image to be processed includes:

Perform noise reduction processing on the image to be processed;

The noise-reduction processed image is edge-enhanced.

In an embodiment, the performing noise reduction processing on the image to be processed includes:

Obtain the RGB color value of a point to be reduced in the image to be processed;

Taking the point to be reduced as a center, acquiring RGB color values of multiple points within a specified range around it to form an RGB color value sequence;

The median value in the sequence of RGB color values is determined, and the median value is used to replace the RGB color values of the points to be reduced.

In an embodiment, said performing edge enhancement on the image after noise reduction processing includes:

Obtain the RGB color value of a point to be enhanced in the image after noise reduction processing;

Using a preset weight template to perform a weighted summation of the RGB color values of multiple points within a specified range around the point to be enhanced to obtain a weighted sum;

The weighted sum is added to the RGB color value of the point to be enhanced, and the addition result is used to replace the RGB color value of the point to be enhanced.

In an embodiment, the performing color correction on the image after image enhancement includes:

Obtain the RGB color value of a point to be corrected in the image after image enhancement;

Substituting the RGB color value of the point to be corrected into a preset color correction prior model to obtain the corrected RGB color value;

Use the corrected RGB color value to replace the RGB color value of the point to be corrected.

In an embodiment, the color correction a priori model is obtained in advance in the following manner:

Obtain the collection color matrix of multiple color blocks and the color matrix of standard color blocks based on the standard color card;

Substitute the collected color matrix into the formula

Obtain the initial color correction model f(w,X ⁱ ); where X ⁱ is the ith row in the collected color matrix, and X ⁱ =(R ⁱ G ⁱ B ⁱ ), w is the preset weight matrix, w ₁ ~ w ₉ are the element values of the corresponding elements in w;

By formula

As a loss function L(w), and optimize the initial color correction model by solving the minimum value of the loss function L(w) to obtain a color correction prior model;

Among them, output _i is the ith row in the color matrix of the standard color patches, and m is the number of color patches.

In an embodiment, the performing fluorescent marking on the color-corrected image includes:

Obtain the RGB color value of a point to be identified in the color-corrected image;

Substituting the RGB color value of the point to be marked into a preset priori model of fluorescent marking to obtain the marked RGB color value;

Replace the RGB color value of the point to be marked with the marked RGB color value.

In one embodiment, the fluorescent label prior model is obtained in advance in the following manner:

Select designated images that carry fluorescence excitation data and are not marked;

Constructing an RGB color value matrix according to the RGB color values of the pixels located in the identification area in the designated image;

Expanding the characteristics of each element in the RGB color value matrix to form an RGB color value expansion matrix;

Determining the mean value of the element values of the RGB color value expansion matrix;

Determining the Manhattan distance between the element value of each element in the RGB color value expansion matrix and the mean value of the element value to form a Manhattan distance set;

According to the Manhattan distance set, it is determined that each element in the RGB color value expansion matrix is in a specified interval

, And fit the relationship curve F(L) between Manhattan distance and probability; where L _max is the maximum value in the Manhattan distance set;

Obtain the RGB color value of the input point A of the designated model, and determine the Manhattan distance between the input point A and the mean value of the element value;

Substitute the Manhattan distance between the input point A and the mean value of the element into the relationship curve F(L), if F(L) is greater than the preset threshold, it is determined that the input point A is in the fluorescence excitation area of the specified image Point, let the weight w=F(L), and substitute it into the formula A _output =((1-w)*R,(1-w)*G,w*255) to get the output A _{output of} the input point A, as As the a priori model of the fluorescent label of the input point A.

On the other hand, an embodiment of the present application also provides an image processing device of an endoscopic fluorescence system, including:

Image acquisition module for acquiring the image to be processed;

An image enhancement module for performing image enhancement on the image to be processed;

The color correction module is used to perform color correction on the enhanced image;

The fluorescent marking module is used to perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.

On the other hand, the embodiment of the present application also provides another image processing device of an endoscopic fluorescence system, including a memory, a processor, and a computer program stored on the memory, and the computer program is used by the processor. Perform the following steps when running:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

On the other hand, the embodiments of the present application also provide a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

It can be seen from the technical solutions provided by the above embodiments of the application that the image processing method of the endoscopic fluorescent system in the embodiments of the application can mark the fluorescent area on the color image, thereby effectively solving the problem that the single-camera near-infrared imaging system can only display false The problem of color image or black and white image makes the image displayed by the endoscopic fluorescence system more accurately reflect the real situation of the detected area.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments described in this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor. In the attached picture:

FIG. 1 is a flowchart of an image processing method of an endoscopic fluorescence system in some embodiments of this application;

2 is a flowchart of image enhancement processing in the image processing method of the endoscopic fluorescence system in some embodiments of the application;

3 is a flowchart of color correction processing in the image processing method of the endoscopic fluorescence system in some embodiments of the application;

4 is a flowchart of fluorescent marking processing in the image processing method of the endoscopic fluorescent system in some embodiments of the application;

FIG. 5 is a schematic diagram of the Laplacian template used in the image processing method of the endoscopic fluorescence system in some embodiments of the application;

6 is a structural block diagram of an image processing device of an endoscopic fluorescence system in some embodiments of the application;

FIG. 7 is a structural block diagram of an image processing device of an endoscopic fluorescence system in some other embodiments of the application.

detailed description

In order to enable those skilled in the art to better understand the technical solutions in the application, the following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Obviously, the described The embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the protection scope of this application.

Referring to FIG. 1, the image processing method of the endoscopic fluorescence system according to some embodiments of the present application may include the following steps:

S101. Obtain an image to be processed.

In some embodiments of the present application, the acquired image to be processed may carry visible light data and near-infrared light data of the target detection area. Among them, the target detection area may contain a fluorescent contrast agent.

S102: Perform image enhancement on the image to be processed.

In some embodiments of the present application, the image quality can be improved by performing image enhancement on the image to be processed, thereby facilitating the enhancement of the recognizability of the target of interest in the image (for example, a diseased biological tissue structure such as a tumor).

S103: Perform color correction on the image after image enhancement.

In some embodiments of the present application, by performing color correction on the enhanced image, the image can be restored to a true color image that is closer to the real situation of the detected area, thereby further enhancing the recognizability of the target of interest in the image. .

S104: Perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.

In some embodiments of the present application, by performing fluorescent marking on the color-corrected image, the target of interest in the image is more prominent relative to other parts of the image, thereby facilitating accurate identification of the boundary between the target of interest and other parts in the image.

It can be seen that the image processing method of the endoscopic fluorescent system in the above embodiment of the present application can mark the fluorescent area on the color image, thereby effectively solving the problem that the single-camera near-infrared imaging system can only display false color images or black and white images. The problem, so that the image displayed by the endoscopic fluorescence system can more accurately reflect the real situation of the detected area. Therefore, the image processing method of the endoscopic fluorescence system in the above-mentioned embodiment of the present application also lowers the threshold of multispectral video imaging research, expands the space available for optical molecular imaging probes, and extends the research and application of optical molecular imaging. range.

As shown in FIG. 2, in some embodiments of the present application, the image enhancement of the image to be processed may include the following steps:

S1021. Perform noise reduction processing on the image to be processed.

In some embodiments of the present application, any existing image noise reduction processing method may be used to process the image to be processed. Among them, these image noise reduction processing methods may include, but are not limited to, median filtering, mean filtering, Gaussian filtering, and so on. In an exemplary embodiment, the performing noise reduction processing on the image to be processed may include the following steps:

1) Obtain the RGB color value of a point to be reduced in the image to be processed. Among them, the noise reduction point here and the various points mentioned below all refer to the pixels in the image.

2) Taking the point to be noise-reduced as the center, obtaining RGB color values of multiple points within a specified range around it to form an RGB color value sequence. The designated surrounding range can be set as required, for example, it can be 9 adjacent points around it, 25 points or more in the designated surrounding range, etc.

3) Determine the median value in the sequence of RGB color values, and replace the RGB color values of the points to be reduced with the median value. The RGB color value sequence is arranged in order from small to large or large to small. Since noise points are mostly located at the front or end of the RGB color value sequence, the median value of the RGB color value sequence is basically not polluted by noise, so The median value of the sequence of RGB color values can be used to replace the RGB color value of the point to be reduced, so as to realize the noise reduction processing of the point to be reduced.

4) Repeat the above steps to complete the image noise reduction processing of other points in the image to be processed.

S1022, perform edge enhancement on the image after noise reduction processing.

In some embodiments of the present application, the main purpose of image edge enhancement is to enhance the boundary relationship and overlay relationship between different objects of interest in the target detection area (for example, the boundary relationship and overlay relationship between blood vessels and different organs in a biological tissue structure). The edge of the relationship, etc.), through the edge image enhancement, the boundary relationship and the overlap relationship between different objects of interest will be more clear. In some exemplary embodiments of the present application, the image edge enhancement may be implemented by using existing methods such as gradient operator, Roberts operator, prewitt operator, or sobel operator. In an exemplary embodiment, the performing noise reduction processing on the image to be processed may include the following steps:

1) Obtain the RGB color value of a point to be enhanced in the image after noise reduction processing.

2) Using a preset weight template to perform a weighted summation of the RGB color values of multiple points within a specified range around the point to be enhanced to obtain a weighted sum. The weight template may be implemented by using a Laplace template or the like, for example, it may be a laplace 3╳3 template as shown in FIG. 5.

3). Add the weighted sum to the RGB color value of the point to be enhanced, and replace the RGB color value of the point to be enhanced with the addition result, thereby completing the edge enhancement processing of the point to be enhanced.

4) Repeat the above steps to complete the edge enhancement processing for other points in the image after noise reduction processing.

As shown in FIG. 3, in an embodiment of the present application, performing color correction on an image after image enhancement may include the following steps:

1). Obtain the RGB color value of a point to be corrected in the enhanced image.

2) Substituting the RGB color values of the points to be corrected into a preset color correction prior model to obtain the corrected RGB color values.

3) Replace the RGB color value of the point to be corrected with the corrected RGB color value.

4) Repeat the above steps to complete the color correction processing of other points in the image after image enhancement.

Wherein, the color correction prior model can be obtained in advance in the following manner:

1) Obtain the collected color matrix input of m color blocks and the color matrix output of standard color blocks based on the standard color card.

among them,

2) Substitute the collected color matrix into the formula

The initial model obtained color correction f (w, X ^i); wherein, ^X-i to collect color matrix row i, and ^{^{^{X i = (R i G i}}} B i), w is a preset weight matrix, w ₁ to w ₉ are the element values of the corresponding elements in w.

3), by formula

As the loss function L(w), and by solving the minimum value of the loss function L(w), the initial color correction model can be optimized to obtain the color correction prior model; where output _i is the standard color patch color matrix In the i-th row, m is the number of color patches.

It should be noted that the color correction method shown in FIG. 3 is only an exemplary embodiment of the present application. In other embodiments of the present application, other image enhancement algorithms such as gamma algorithm may also be used for implementation, which is not limited in this application. .

As shown in FIG. 4, in some embodiments of the present application, performing fluorescent marking on the color-corrected image may include the following steps:

1) Get the RGB color value of a point to be identified in the color-corrected image.

2) Substituting the RGB color values of the points to be marked into the preset a priori model of fluorescent marking to obtain the marked RGB color values.

3) Replace the RGB color value of the point to be marked with the marked RGB color value.

4) Repeat the above steps to complete the fluorescent marking processing of other points in the color-corrected image.

Wherein, the priori model of the fluorescent label can be obtained in advance in the following manner:

1). Select designated images that carry fluorescence excitation data and are not marked.

2) Construct an RGB color value matrix according to the RGB color values of the pixels located in the identification area in the designated image. Wherein, the identification area in the designated image may be determined in advance based on the analyzed image.

3) Expand the characteristics of each element in the RGB color value matrix to form an RGB color value expansion matrix. A pixel is composed of three basic features, R, G, and B. These three independent dimensions are directly used as features for processing, which will lead to inaccurate regional classification and recognition due to too few features, so the three basic features are expanded. In an exemplary embodiment, if the RGB color value matrix is expressed as:

Then the corresponding RGB color value expansion matrix can be expressed as:

4) Determine the mean value of the element values of the RGB color value expansion matrix. In an exemplary embodiment, the mean value of the element values of the RGB color value expansion matrix can be expressed as:

5) Determine the Manhattan distance between the element value of each element in the RGB color value expansion matrix and the mean value of the element value to form a Manhattan distance set. In an exemplary embodiment, the calculation formula of the Hatton distance is as follows:

Among them, L represents the Manhattan distance between inputExtend _m and inputExtendAvg.

6) Determine that each element in the RGB color value expansion matrix is in a specified interval according to the Manhattan distance set

And fit the relationship curve F(L) between Manhattan distance and probability; where L _max is the maximum value in the Manhattan distance set.

7) Obtain the RGB color value of the input point A of the designated model, and determine the Manhattan distance between the input point A and the mean value of the element value.

8). Substitute the Manhattan distance between the input point A and the mean value of the element into the relationship curve F(L), if F(L) is greater than a preset threshold (in an exemplary embodiment, the threshold may be 0.8, for example. Etc.), the input point A is determined to be a point in the fluorescence excitation region of the designated image, and the weight value w=F(L) is substituted into the formula A _output =((1-w)*R,(1-w )*G,w*255) Obtain the output A _{output of} the input point A as a priori model of the fluorescent mark of the input point A.

9). Repeat the above steps 7) to 8) to obtain the priori model of fluorescent markers for all input points of the specified model, and then form a priori model of total fluorescent markers.

It should be understood that the above-mentioned method for constructing a priori model of fluorescent markers is only an exemplary embodiment of the present application. In other embodiments of the present application, other machine learning algorithms (such as support vector machines, decision trees, neural networks, etc.) may also be used. ) And other implementations, this application does not limit this.

Referring to FIG. 6, corresponding to the image processing method of the endoscopic fluorescence system described above, the image processing apparatus of the endoscopic fluorescence system of some embodiments of the present application may include:

The image acquisition module 61 can be used to acquire an image to be processed;

The image enhancement module 62 may be used to perform image enhancement on the image to be processed;

The color correction module 63 can be used to perform color correction on the image after image enhancement;

The fluorescent marking module 64 can be used to perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing this application, the functions of each unit can be implemented in the same one or more software and/or hardware.

Referring to FIG. 7, corresponding to the image processing method of the endoscopic fluorescence system described above, the image processing apparatus of the endoscopic fluorescence system of other embodiments of the present application may include a memory, a processor, and a storage device stored on the memory. A computer program, when the computer program is run by the processor, the following steps are executed:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

Although the process flow described above includes multiple operations appearing in a specific order, it should be clearly understood that these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel (for example, using parallel processors or Multi-threaded environment).

The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

In a typical configuration, the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.

Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

It should also be noted that the terms "including", "including" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, or device including a series of elements not only includes those elements, but also includes no Other elements clearly listed, or they also include elements inherent to the process, method, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other same elements in the process, method, or device that includes the element.

Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The above descriptions are only examples of this application and are not used to limit this application. For those skilled in the art, this application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the scope of the claims of this application.

Claims

An image processing method of an endoscopic fluorescence system, characterized in that it comprises:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

Perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.
The image processing method of the endoscopic fluorescence system according to claim 1, wherein said performing image enhancement on the image to be processed comprises:

Perform noise reduction processing on the image to be processed;

The noise-reduction processed image is edge-enhanced.
3. The image processing method of the endoscopic fluorescence system according to claim 2, wherein the denoising processing of the image to be processed comprises:

Obtain the RGB color value of a point to be reduced in the image to be processed;

Taking the point to be reduced as a center, acquiring RGB color values of multiple points within a specified range around it to form an RGB color value sequence;

The median value in the sequence of RGB color values is determined, and the median value is used to replace the RGB color values of the points to be reduced.
3. The image processing method of the endoscopic fluorescence system according to claim 2, wherein said performing edge enhancement on the image after noise reduction processing comprises:

Obtain the RGB color value of a point to be enhanced in the image after noise reduction processing;

Using a preset weight template to perform a weighted summation of the RGB color values of multiple points within a specified range around the point to be enhanced to obtain a weighted sum;

The weighted sum is added to the RGB color value of the point to be enhanced, and the addition result is used to replace the RGB color value of the point to be enhanced.
5. The image processing method of the endoscopic fluorescence system according to claim 1, wherein said performing color correction on the image after image enhancement comprises:

Obtain the RGB color value of a point to be corrected in the image after image enhancement;

Substituting the RGB color value of the point to be corrected into a preset color correction prior model to obtain the corrected RGB color value;

Use the corrected RGB color value to replace the RGB color value of the point to be corrected.
7. The image processing method of the endoscopic fluorescence system according to claim 5, wherein the color correction prior model is obtained in advance in the following manner:

Obtain the collection color matrix of multiple color blocks and the color matrix of standard color blocks based on the standard color card;

Substitute the collected color matrix into the formula
Obtain the initial color correction model f(w,X i ); where X i is the ith row in the collected color matrix, and X i =(R i G i B i ), w is the preset weight matrix, w 1 ~ w 9 are the element values of the corresponding elements in w;

By formula
As a loss function L(w), and optimize the initial color correction model by solving the minimum value of the loss function L(w) to obtain a color correction prior model;

Among them, output i is the ith row in the color matrix of the standard color patches, and m is the number of color patches.
5. The image processing method of an endoscopic fluorescence system according to claim 1, wherein said performing fluorescence marking on the color-corrected image comprises:

Obtain the RGB color value of a point to be identified in the color-corrected image;

Substituting the RGB color value of the point to be marked into a preset priori model of fluorescent marking to obtain the marked RGB color value;

Replace the RGB color value of the point to be marked with the marked RGB color value.
7. The image processing method of the endoscopic fluorescence system according to claim 7, wherein the priori model of the fluorescent marker is obtained in advance in the following manner:

Select designated images that carry fluorescence excitation data and are not marked;

Constructing an RGB color value matrix according to the RGB color values of the pixels located in the identification area in the designated image;

Expanding the characteristics of each element in the RGB color value matrix to form an RGB color value expansion matrix;

Determining the mean value of the element values of the RGB color value expansion matrix;

Determining the Manhattan distance between the element value of each element in the RGB color value expansion matrix and the mean value of the element value to form a Manhattan distance set;

According to the Manhattan distance set, it is determined that each element in the RGB color value expansion matrix is in a specified interval
, And fit the relationship curve F(L) between Manhattan distance and probability; where L max is the maximum value in the Manhattan distance set;

Obtain the RGB color value of the input point A of the specified model, and determine the Manhatten distance between the input point A and the mean value of the element;

Substitute the Manhattan distance between the input point A and the mean value of the element into the relationship curve F(L), if F(L) is greater than the preset threshold, it is determined that the input point A is in the fluorescence excitation area of the specified image Point, let the weight w=F(L), and substitute it into the formula A output =((1-w)*R,(1-w)*G,w*255) to get the output A output of the input point A, as As the a priori model of the fluorescent label of the input point A.
An image processing device of an endoscopic fluorescence system, characterized in that it comprises:

Image acquisition module for acquiring the image to be processed;

An image enhancement module for performing image enhancement on the image to be processed;

The color correction module is used to perform color correction on the enhanced image;

The fluorescent marking module is used to perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.
An image processing device of an endoscopic fluorescence system, comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program is run by the processor to execute the following steps:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

Perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.
A computer storage medium with a computer program stored thereon, wherein the computer program is executed by a processor to implement the following steps:

Obtain the image to be processed;

Performing image enhancement on the image to be processed;

Perform color correction on the enhanced image;

Perform fluorescent marking on the color-corrected image to obtain a color image with fluorescent display.